tooluniverse-rare-disease-diagnosis
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted clinical descriptions and patient identifiers to automate complex research workflows including network searches and report generation.
- Ingestion points: User-provided symptoms in the
standardize_phenotypelogic, patient IDs for file naming, and genetic variant strings for interpretation. - Boundary markers: None detected. User input is directly interpolated into tool queries and markdown report templates without delimiters or instructions to ignore embedded commands.
- Capability inventory: The skill utilizes a broad range of capabilities including network operations (accessing over 20 medical/genetic databases) and file system writes (creating
.mdand.csvreports). - Sanitization: There are no instructions for the agent to sanitize or validate external content before passing it to tool parameters or writing it to the local file system.
Audit Metadata